# Loading dataset
X = load_x_dataset1()
y = load_y_dataset1()
# building the mode
model = Sequential()
model.add(Conv2D(32, kernel_size=(5, 5), strides=(1, 1), activation='relu', input_shape=X.shape[1:]))
model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2)))
model.add(Conv2D(64, (5, 5), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Flatten())
model.add(Dense(1000, activation='relu'))
model.add(Dense(5, activation='softmax'))
# Stops the training early of the val_loss has stopped improving
early_stop = EarlyStopping(monitor="val_loss", min_delta=0, patience=2, verbose=0, mode="auto",
baseline=None, restore_best_weights=False)
model.compile(loss='sparse_categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
model.summary()
history = model.fit(X, y, batch_size=150, epochs=6, verbose=1, validation_split=0.2, callbacks=[early_stop])
# Plot training & validation accuracy & loss values
plot_model(history, 'acc', 'McQueen', '/Users/william/Documents/gitHub/B20IT38/mcqueen_models/models/mcqueen_phase_three/base/acc.png')
plot_model(history, 'loss', 'McQueen', '/Users/william/Documents/gitHub/B20IT38/mcqueen_models/models/base/loss.png')
# Saving the model
model.save(NAME + '.model')
test_model(NAME + '.model')
# Load dataset
X = load_x_1()
y = load_y_1()
# Load model, create early stop callback & train model
history = train_model(
X=X,
y=y,
epochs=30,
batch_size=150,
val_split=0.3,
patience=1,
model=
"/Users/william/Documents/gitHub/B20IT38/mcqueen_models/mcqueen_pase_two/McQueen.model",
save_location=FOLDER + NAME + '.model')
# Plot training & validation acc & loss
plot_model(history=history,
metric='acc',
name=NAME,
save_location=FOLDER + 'acc.png')
plot_model(history=history,
metric='loss',
name=NAME,
save_location=FOLDER + 'loss.png')
# Test the trained model against the testing set
# Function prints how many correct predictions that was made.
# test_model(FOLDER+NAME+'.model')
metrics=['accuracy'])
# Stops the training early of the val_loss has stopped improving
early_stop = EarlyStopping(monitor="val_loss",
min_delta=0,
patience=7,
verbose=0,
mode="auto",
baseline=None,
restore_best_weights=False)
# Trains the model and saves the history of the training
history = model.fit(X,
y,
batch_size=150,
epochs=100,
validation_split=0.2,
callbacks=[early_stop])
# Plotting the acc & loss of the training and validation
plot_model(
history, 'acc', 'McQueen_Fully_connected',
'/Users/william/Documents/gitHub/B20IT38/mcqueen_models/mcqueen_FF/base/acc.png'
)
plot_model(
history, 'loss', 'McQueen_Fully_connected',
'/Users/william/Documents/gitHub/B20IT38/mcqueen_models/mcqueen_FF/base/loss.png'
)
model.save(NAME + '.model') # Saving the model
test_model(NAME + '.model') # Testing the model with testset1
# Stops the training early of the val_loss has stopped improving
early_stop = EarlyStopping(monitor="val_loss",
min_delta=0,
patience=3,
verbose=0,
mode="auto",
baseline=None,
restore_best_weights=False)
# Trains the model and saves the history of the training
history = model.fit(X,
y,
batch_size=320,
epochs=15,
validation_split=0.2,
callbacks=[early_stop])
model.summary()
# Plotting the acc & loss of the training and validation
plot_model(
history, 'acc', 'McQueen_Phase_Two_CNN',
'/Users/william/Documents/gitHub/B20IT38/mcqueen_models/mcqueen_pase_two/acc.png'
)
plot_model(
history, 'loss', 'McQueen_Phase_Two_CNN',
'/Users/william/Documents/gitHub/B20IT38/mcqueen_models/mcqueen_pase_two/loss.png'
)
model.save(NAME + '.model') # Saving the model
# test_model(NAME+'.model') # Testing the model with testset1
model.add(Dense(350, activation='relu'))
model.add(Dense(6, activation='softmax'))
early_stop = EarlyStopping(monitor="val_loss",
min_delta=0,
patience=2,
verbose=0,
mode="auto",
baseline=None,
restore_best_weights=True)
model.compile(optimizer=SGD(lr=0.001, momentum=0.8, decay=1e-6),
loss='sparse_categorical_crossentropy',
metrics=['accuracy'])
# Trains the model and saves the history of the training
history = model.fit(X,
y,
batch_size=200,
epochs=10,
validation_split=0.3,
callbacks=[early_stop])
model.summary()
# Plotting the acc & loss of the training and validation
plot_model(history, 'acc', 'McQueen_p3_t1', FOLDER + 'acc.png')
plot_model(history, 'loss', 'McQueen_P3_t1', FOLDER + 'loss.png')
model.save(NAME + '.model') # Saving the model
# test_model(NAME+'.model') # Testing the model with testset1